Skip to main content
Glama
UpendraNath

Tavily Web Search MCP Server

by UpendraNath

roll_dice

Simulate dice rolls using standard notation to generate random numbers for games, probability calculations, or decision-making.

Instructions

Roll the dice with the given notation

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
notationYes
num_rollsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • server.py:21-25 (handler)
    The main handler function for the 'roll_dice' MCP tool, decorated with @mcp.tool() which registers it with the FastMCP server. It instantiates DiceRoller and returns its string representation containing the roll results.
    @mcp.tool()
    def roll_dice(notation: str, num_rolls: int = 1) -> str:
        """Roll the dice with the given notation"""
        roller = DiceRoller(notation, num_rolls)
        return str(roller)
  • Core implementation of dice rolling logic within DiceRoller class: parses dice notation (e.g., '2d6k1'), generates random rolls, sorts descending, keeps top N rolls, and returns all rolls and kept rolls.
    def roll_dice(self):
        match = self.dice_pattern.match(self.notation)
        if not match:
            raise ValueError("Invalid dice notation")
    
        num_dice = int(match.group(1))
        dice_sides = int(match.group(2))
        keep = int(match.group(4)) if match.group(4) else num_dice
    
        rolls = [random.randint(1, dice_sides) for _ in range(num_dice)]
        rolls.sort(reverse=True)
        kept_rolls = rolls[:keep]
    
        return rolls, kept_rolls
  • __str__ method of DiceRoller that formats the output string returned by the tool handler. Handles single or multiple rolls, calling roll_dice() or roll_multiple().
    def __str__(self):
        if self.num_rolls == 1:
            rolls, kept_rolls = self.roll_dice()
            return f"ROLLS: {', '.join(map(str, rolls))} -> RETURNS: {sum(kept_rolls)}"
        else:
            results = self.roll_multiple()
            result_strs = []
            for i, result in enumerate(results, 1):
                result_strs.append(f"Roll {i}: ROLLS: {', '.join(map(str, result['rolls']))} -> RETURNS: {result['total']}")
            return "\n".join(result_strs)
  • DiceRoller class initialization, storing notation and num_rolls, compiling regex for parsing dice notation supporting 'NdSk' format.
    class DiceRoller:
        def __init__(self, notation, num_rolls=1):
            self.notation = notation
            self.num_rolls = num_rolls
            self.dice_pattern = re.compile(r"(\d+)d(\d+)(k(\d+))?")
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states the action but doesn't disclose behavioral traits like whether rolls are random, if results are deterministic, error handling for invalid notation, or output format. This is a significant gap for a tool with parameters and an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no wasted words. It's front-loaded and appropriately sized for the tool's complexity, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 2 parameters with 0% schema coverage and an output schema, the description is incomplete. It hints at the 'notation' parameter but doesn't fully explain it or cover 'num_rolls'. The output schema likely handles return values, so that's not needed, but the description lacks sufficient detail for effective use without additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions 'notation' but doesn't explain what dice notation entails (e.g., '2d6' for two six-sided dice). The 'num_rolls' parameter isn't addressed at all. The description adds minimal meaning beyond the schema, failing to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Roll the dice with the given notation' states the action (roll) and resource (dice) but is vague about what 'notation' means. It doesn't differentiate from sibling tools like 'load_bookmark_data' or 'organize_and_categorize', but those are unrelated, so differentiation isn't needed. The purpose is understandable but lacks specificity about dice notation formats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention any context, prerequisites, or exclusions. Since sibling tools are unrelated (e.g., web_search), there's no explicit comparison, leaving usage unclear beyond the basic action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/UpendraNath/MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server